Reproduce “Noisy Issues, Noisy Results: Mislabeling in Information Retrieval-based Bug Localization” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Moumita Asad, Rafed Muhammad Yasir, Yirui He, Ziyao He, Sam Malek
The authors examine how issue-tracker labels affect file-level bug localization evaluation. They classify reports across five benchmarks and compare six techniques on the Ye et al. benchmark before and after removing suspected non-bugs from the test set. Non-bugs make up 29.01% to 44.01% of reports; all six techniques’ MRR falls, but the performance-impact results are limited to this benchmark and these methods.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.